© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212449
    Prev
    Next
    INDEX
    Explanations

    describing people and options

    np_acts-logits-general · gemini-2.5-flash-lite

    specific states or files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stunts
    0.49
    d
    0.48
    x
    0.48
     behaviors
    0.44
     payloads
    0.44
    t
    0.44
     activ
    0.43
     initiatives
    0.43
     stagger
    0.43
     empowers
    0.43
    POSITIVE LOGITS
    掬
    0.61
     する
    0.55
     Johannesburg
    0.52
     mancan
    0.52
     Berkeley
    0.51
     Schweizer
    0.51
    মিল
    0.49
     Winkler
    0.49
     Lieben
    0.48
     Trabalho
    0.48
    Activations Density 0.000%

    No Known Activations